INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inus

-0.08

allon

-0.08

 dispens

-0.08

chester

-0.08

 concessions

-0.08

orman

-0.08

alic

-0.07

'l

-0.07

 Reception

-0.07

igers

-0.07

POSITIVE LOGITS

/OR

0.12

ernet

0.10

nP

0.10

mmo

0.10

{*}

0.10

%n

0.10

Gat

0.10

*((

0.10

 uncert

0.10

mag

0.10

Activations Density 0.000%

No Known Activations